《《eScholarship UC item 5nn455bt》.pdf

Department of Statistics, UCLA UC Los Angeles Peer Reviewed Title: Image Parsing: Unifying Segmentation, Detection, and Recognition Author: Tu, Zhuowen Chen, Xiangrong Yuille, Alan Zhu, Song Chun Publication Date: 10-20-2005 Series: Department of Statistics Papers Publication Info: Department of Statistics Papers, Department of Statistics, UCLA, UC Los Angeles Permalink: /uc/item/5nn455bt eScholarship provides open access, scholarly publishing services to the University of California and delivers a dynamic research platform to scholars worldwide. Image Parsing: Unifying Segmentation, Detection, and Recognition Zhuowen Tu, Xiangrong Chen, Alan Yuille, and Song Chun Zhu Department of Statistics, UCLA. Los Angeles, CA 90095. USA {ztu,xrchen,yuille,sczhu}@ Abstract. In this chapter we present a Bayesian framework for pars- ing images into their constituent visual patterns. The parsing algorithm optimizes the posterior probability and outputs a scene representation as a “parsing graph”, in a spirit similar to parsing sentences in speech and natural language. The algorithm constructs the parsing graph and re-configures it dynamically using a set of moves, which are mostly re- versible Markov chain jumps. This computational framework integrates two popular inference approaches – generative (top-down) methods and discriminative (bottom-up) methods. The former formulates the pos- terior probability in terms of gen